adammandic87 commited on
Commit
6a0171c
·
verified ·
1 Parent(s): 2ee152d

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc81f57fb8487e09ffe23c06a3fd903b040943ea9b3728011f2a74ca6a87f81f
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b17327c31d30633ad9367bd2abd24aaf0af5c577a98150a6afb94ccf48959e
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a9a5a305b586d330ffa162c50da27c508fe0707ee08edfb441a0586f5542d69
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:281a4f6424450448c8e0f597da0779d60d800e475f9076340b5daa3bb3c5967a
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9908c81d4f08fa0707f543eeeb598037560bf300bf9c35b62655c74c41b96908
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b51af41e21b1e50a7239889a0695d87b128e603cc3df58acf5c3bb469524745
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.00024789803127646826,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 46.215,
74
  "eval_steps_per_second": 23.11,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 194578955108352.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0003718470469147024,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 46.215,
74
  "eval_steps_per_second": 23.11,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0002892143698225463,
79
+ "grad_norm": 1.6822401285171509,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.1236,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003305307083686244,
86
+ "grad_norm": 1.1016179323196411,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.671,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003718470469147024,
93
+ "grad_norm": 1.5902749300003052,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.8739,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003718470469147024,
100
+ "eval_loss": 3.211221933364868,
101
+ "eval_runtime": 219.8062,
102
+ "eval_samples_per_second": 46.364,
103
+ "eval_steps_per_second": 23.184,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 291868432662528.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null